Hi everyone, I wonder that can I write same nn module on Pytorch
My keras codes are:
model = Sequential()
# model.add(LSTM(12, input_shape=train_x.shape[1:], return_sequences=True))
# model.add(Activation('tanh'))
# model.add(LSTM(32, input_shape=train_x.shape[1:], return_sequences=False))
model.add(LSTM(16, input_shape=(1, 3), return_sequences=False))
model.add(Activation('relu'))
# model.add(Dense(12, input_shape=train_x.shape[1:]))
# model.add(Activation('relu'))
model.add(Dense(12))
model.add(Activation('relu'))
model.add(Dense(1))
model.compile(loss='mse',
optimizer='adam',
metrics=['mse'])
model.fit(train_x, train_y,
batch_size=batch_size,
epochs=500,
validation_data=(val_x, val_y),
callbacks = [tensorboard_CB])
I have been trying for one week to write this in PyTorch but I confront with problem which is train_x=[23k,1,3] and train_y=[23k,1] so their shapes are not same so I cannot train nn on PyTorch